action-priority-matrix
This skill computes Risk Priority Numbers by multiplying severity, occurrence, and detection scores, then classifies failure modes into High, Medium, or Low action priorities using AIAG-VDA standard thresholds. Use it during failure mode and effects analysis to systematically rank which risks require immediate mitigation versus monitoring, with explicit identification of borderline cases near priority boundaries.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/action-priority-matrix && cp -r /tmp/action-priority-matrix/skills/action-priority-matrix ~/.claude/skills/action-priority-matrixSKILL.md
# Action Priority Matrix Computes RPN and classifies failure modes into High/Medium/Low action priority. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Why Subagent Priority classification requires mechanical computation followed by judgment on borderline cases. Isolated context ensures consistent application of thresholds. ## Input - **severity_scores**: S scores for all failure modes - **occurrence_scores**: O scores for all failure modes - **detection_scores**: D scores for all failure modes ## Output - **priority_matrix**: Full table with S, O, D, RPN, and H/M/L classification - **action_required**: H-priority items requiring mandatory mitigation - **borderline_cases**: Items near threshold boundaries <!-- BEGIN available-tables (generated) --> ## Available SOPs Optional, no fixed order; the final leaf is always a sop. | SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. | <!-- END available-tables (generated) -->
Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems